Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 430 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.9723. Min Act: -0.0001

Data Index: 993739 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8908. Min Act: -0.0001

Data Index: 442574 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8359. Min Act: -0.0001

Data Index: 739880 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8656. Min Act: -0.0001

Data Index: 698403 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8231. Min Act: -0.0001

Data Index: 690228 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8438. Min Act: -0.0001

Data Index: 409478 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7732. Min Act: -0.0001

Data Index: 675163 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7634. Min Act: -0.0001

Data Index: 955938 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7522. Min Act: -0.0001

Data Index: 159621 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7439. Min Act: -0.0001

Data Index: 1226406 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7626. Min Act: -0.0001

Data Index: 1024144 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8041. Min Act: -0.0001

Data Index: 866202 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7563. Min Act: -0.0001

Data Index: 638062 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1158852 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7042. Min Act: -0.0001

Data Index: 651497 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6981. Min Act: -0.0001

Data Index: 374598 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6901. Min Act: -0.0001

Data Index: 568309 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6958. Min Act: -0.0001

Data Index: 593022 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6903. Min Act: -0.0001

Data Index: 860527 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6838. Min Act: -0.0001

Data Index: 812629 (C4 (Web Text))

Max Activating Token Index: 493